Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    describes creative output characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Possibly
    0.50
    possibly
    0.50
     possibly
    0.49
    Possibly
    0.47
     शायद
    0.47
     potentially
    0.46
     Represent
    0.46
    probably
    0.45
    可能的
    0.43
     probably
    0.43
    POSITIVE LOGITS
     characterised
    0.78
     characterized
    0.68
     отличаются
    0.64
     hänen
    0.61
    characterized
    0.61
     characterizes
    0.59
     infused
    0.57
     그의
    0.57
     characterize
    0.56
     imbued
    0.55
    Act Density 0.037%

    No Known Activations